{"id":"https://openalex.org/W7223803429","doi":"https://doi.org/10.5281/zenodo.23704662","title":"AgentFail: A Stateful Paradigm for Quantifying Autonomous Agent Over-Reliance and Multi-Turn Operational Failures","display_name":"AgentFail: A Stateful Paradigm for Quantifying Autonomous Agent Over-Reliance and Multi-Turn Operational Failures","publication_year":2026,"publication_date":"2026-10-27","ids":{"openalex":"https://openalex.org/W7223803429","doi":"https://doi.org/10.5281/zenodo.23704662"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.23704662","doi":"https://doi.org/10.5281/zenodo.23704662","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23704662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.23704662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5159761834","display_name":"KEMISOLA OWONIYA","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"OWONIYA, KEMISOLA","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5159761834"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.80240237,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.49390000104904175,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.49390000104904175,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.2563000023365021,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13295","display_name":"Safety Systems Engineering in Autonomy","score":0.07639999687671661,"subfield":{"id":"https://openalex.org/subfields/2213","display_name":"Safety, Risk, Reliability and Quality"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/autonomous-ai-agents","display_name":"autonomous AI agents","score":0.8610000014305115},{"id":"https://openalex.org/keywords/llm-safety-evaluation","display_name":"LLM safety evaluation","score":0.6169999837875366},{"id":"https://openalex.org/keywords/data-deletion","display_name":"data deletion","score":0.4009999930858612},{"id":"https://openalex.org/keywords/privacy-violations","display_name":"privacy violations","score":0.8420000076293945},{"id":"https://openalex.org/keywords/safety-guardrails","display_name":"safety guardrails","score":0.5910000205039978},{"id":"https://openalex.org/keywords/alignment-strategies","display_name":"alignment strategies","score":0.5320000052452087},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5690000057220459}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7075999975204468},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.444599986076355},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.4318999946117401},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.3978999853134155},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38749998807907104},{"id":"https://openalex.org/C22927095","wikidata":"https://www.wikidata.org/wiki/Q1784206","display_name":"Stateful firewall","level":3,"score":0.37369999289512634},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.3610999882221222},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3546000123023987},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3382999897003174},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.32179999351501465},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.303600013256073},{"id":"https://openalex.org/C14185376","wikidata":"https://www.wikidata.org/wiki/Q30232","display_name":"Agile software development","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C111498074","wikidata":"https://www.wikidata.org/wiki/Q173326","display_name":"Formal verification","level":2,"score":0.27950000762939453},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27950000762939453},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C163707989","wikidata":"https://www.wikidata.org/wiki/Q1996307","display_name":"Life-critical system","level":3,"score":0.2630000114440918},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.5281/zenodo.23704662","doi":"https://doi.org/10.5281/zenodo.23704662","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23704662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},{"id":"doi:10.5281/zenodo.23704663","doi":"https://doi.org/10.5281/zenodo.23704663","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23704663","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.5281/zenodo.23704662","doi":"https://doi.org/10.5281/zenodo.23704662","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.23704662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7110894099","https://openalex.org/W7154982133","https://openalex.org/W7155881287","https://openalex.org/W7164034352","https://openalex.org/W7167691546","https://openalex.org/W4405627542","https://openalex.org/W7159956031","https://openalex.org/W7161028153","https://openalex.org/W7084084590","https://openalex.org/W7207738045"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"Large":[2],"Language":[3],"Models":[4],"(LLMs)":[5],"transition":[6],"from":[7],"passive":[8],"text":[9],"generators":[10],"to":[11,66,198],"autonomous":[12,47],"AI":[13],"agents":[14],"executing":[15,123],"multi-step":[16],"workflows,":[17],"evaluating":[18],"their":[19],"operational":[20,44,100],"safety":[21,146,196],"becomes":[22],"a":[23,108,155,192],"critical,":[24],"unsolved":[25],"bottleneck.":[26],"Current":[27],"evaluation":[28,165,188],"frameworks":[29],"heavily":[30],"prioritize":[31],"conversational":[32],"fluency":[33],"or":[34,148],"static":[35],"reasoning,":[36],"completely":[37],"ignoring":[38],"the":[39,173,200],"severe":[40],"financial,":[41],"legal,":[42],"and":[43,70,86,103,134,172,186,205],"risks":[45],"of":[46,140,158,202],"actions":[48],"in":[49,111],"live":[50],"software":[51,81],"environments.":[52],"To":[53],"bridge":[54],"this":[55],"critical":[56,130],"gap,":[57],"we":[58,190],"introduce":[59,154],"AgentFail,":[60],"an":[61],"open-source,":[62],"turnkey":[63],"benchmark":[64],"engineered":[65],"evaluate":[67],"agentic":[68,159,209],"over-reliance":[69],"catastrophic":[71],"failure":[72,160],"modes":[73],"across":[74],"leading":[75],"LLM":[76],"architectures":[77],"within":[78],"Dockerized":[79],"enterprise":[80],"environments":[82],"(including":[83],"Salesforce,":[84],"Jira,":[85],"SQL-based":[87],"ERP":[88],"networks).":[89],"Comprising":[90],"500":[91],"complex,":[92],"multi-turn":[93],"corporate":[94],"task":[95],"scenarios":[96],"embedded":[97],"with":[98],"subtle":[99],"edge":[101],"cases":[102],"ambiguous":[104],"constraints,":[105],"AgentFail":[106],"exposes":[107],"pervasive":[109],"vulnerability":[110],"frontier":[112],"architectures:":[113],"current":[114],"state-of-the-art":[115],"reasoning":[116],"models":[117],"exhibit":[118],"acute":[119],"automation":[120],"over-reliance,":[121],"confidently":[122],"destructive":[124],"actions\u2014such":[125],"as":[126],"unauthorized":[127],"data":[128,136],"deletion,":[129],"financial":[131],"ledger":[132],"miscalculations,":[133],"privacy-violating":[135],"distributions\u2014in":[137],"over":[138],"42%":[139],"empirical":[141],"trials":[142],"without":[143],"triggering":[144],"built-in":[145],"overrides":[147],"initiating":[149],"human":[150],"validation":[151],"requests.":[152],"We":[153],"formal":[156],"taxonomy":[157],"alongside":[161],"two":[162],"novel":[163],"continuous":[164],"metrics:":[166],"Error":[167],"Propagation":[168],"Velocity":[169],"(Vep":[170],")":[171],"Over-Reliance":[174],"Coefficient":[175],"(\u03a9).":[176],"By":[177],"open-sourcing":[178],"our":[179],"entire":[180],"testing":[181],"infrastructure,":[182],"automated":[183],"environment":[184],"wrappers,":[185],"baseline":[187,197],"suite,":[189],"provide":[191],"rigorous,":[193],"highly":[194],"transferable":[195],"accelerate":[199],"development":[201],"alignment":[203],"strategies":[204],"guardrails":[206],"for":[207],"next-generation":[208],"workflows.":[210]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-10-28T00:00:00"}
